KDE Density Score

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Kernel Density Estimation (KDE)method0.828
  Used in NIS+ to estimate natural distribution p(yt) for inverse probability weight.
• Feature Densityconcept0.748
  Fraction of training tokens on which a given feature has nonzero activation; used as proxy metric for autoencoder quality
• conditional densitiesconcept0.719
  Time-dependent densities of states and parameters obtained by maximizing free energy.
• Feature Density Histogrammethod0.708
  Log-scale histogram of feature firing rates used as proxy for autoencoder quality during hyperparameter tuning
• Density of Centersconcept0.696
  The degree to which centers are packed and overlapped, contributing to the life of the whole.
• Recognition Densityconcept0.687
  Approximate posterior probability distribution embodied in organism's internal states; organism's best guess about causes of sensations
• High Density Feature Clusterconcept0.676
  Mode in feature density histogram around 1e-5 corresponding to interpretable features, contrasted with ultralow density cluster
• Density Model of Self-Experienceconcept0.675
  The self-prior functions as a density model over the agent's familiar multisensory states in latent space